Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 11980
    Prev
    Next
    INDEX
    Explanations

    USB endpoint

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ثق
    -0.08
    maßen
    -0.08
     quot
    -0.07
    abcdefghijklmnopqrstuvwxyz
    -0.07
     Fergus
    -0.07
     Polski
    -0.07
     Ты
    -0.07
     Andrea
    -0.07
     brute
    -0.07
     modern
    -0.07
    POSITIVE LOGITS
    Homepage
    0.08
    Odd
    0.08
    ?r
    0.08
     odd
    0.08
    Multipart
    0.08
    首頁
    0.08
     drum
    0.08
    져
    0.08
    Signed
    0.08
    Compression
    0.08
    Activations Density 0.000%

    No Known Activations